Spaces:
Running on Zero
Running on Zero
| import tempfile | |
| import unittest | |
| from pathlib import Path | |
| from zsgdp.benchmarks.parser_quality import run_parser_benchmark | |
| from zsgdp.cli import main | |
| class BenchmarkTests(unittest.TestCase): | |
| def test_run_parser_benchmark_writes_results(self): | |
| with tempfile.TemporaryDirectory() as tmp: | |
| tmp_path = Path(tmp) | |
| docs = tmp_path / "docs" | |
| out = tmp_path / "bench" | |
| docs.mkdir() | |
| (docs / "one.md").write_text("# One\n\nHello world", encoding="utf-8") | |
| summary = run_parser_benchmark(docs, out) | |
| self.assertEqual(summary["document_count"], 1) | |
| self.assertIn("fixed_token_baseline", summary["documents"][0]["chunk_strategy_counts"]) | |
| self.assertTrue(summary["chunk_strategy_leaderboard"]) | |
| self.assertIn("structure_quality", summary) | |
| self.assertIn("chunking_quality", summary) | |
| self.assertIn("throughput", summary) | |
| self.assertIn("ablation_plan", summary) | |
| self.assertTrue((out / "results.json").exists()) | |
| self.assertTrue((out / "leaderboard.csv").exists()) | |
| self.assertTrue((out / "parser_runs.csv").exists()) | |
| self.assertTrue((out / "chunk_runs.csv").exists()) | |
| self.assertTrue((out / "structure_runs.csv").exists()) | |
| self.assertTrue((out / "chunk_quality.csv").exists()) | |
| self.assertTrue((out / "throughput_runs.csv").exists()) | |
| self.assertTrue((out / "ablations.json").exists()) | |
| def test_benchmark_cli(self): | |
| with tempfile.TemporaryDirectory() as tmp: | |
| tmp_path = Path(tmp) | |
| docs = tmp_path / "docs" | |
| out = tmp_path / "bench" | |
| docs.mkdir() | |
| (docs / "one.md").write_text("# One\n\nHello world", encoding="utf-8") | |
| code = main(["benchmark", "--input", str(docs), "--output", str(out), "--parsers", "text"]) | |
| self.assertEqual(code, 0) | |
| self.assertTrue((out / "leaderboard.csv").exists()) | |
| self.assertTrue((out / "chunk_runs.csv").exists()) | |
| self.assertTrue((out / "structure_runs.csv").exists()) | |
| self.assertTrue((out / "chunk_quality.csv").exists()) | |
| self.assertTrue((out / "throughput_runs.csv").exists()) | |
| if __name__ == "__main__": | |
| unittest.main() | |